Pablo Samuel Castro
Cited by
Cited by
From taxi GPS traces to social and community dynamics: A survey
PS Castro, D Zhang, C Chen, S Li, G Pan
ACM Computing Surveys (CSUR) 46 (2), 1-34, 2013
Urban traffic modelling and prediction using large scale taxi GPS traces
PS Castro, D Zhang, S Li
International Conference on Pervasive Computing, 57-72, 2012
iBOAT: Isolation-based online anomalous trajectory detection
C Chen, D Zhang, PS Castro, N Li, L Sun, S Li, Z Wang
IEEE Transactions on Intelligent Transportation Systems 14 (2), 806-818, 2013
Real-time detection of anomalous taxi trajectories from GPS traces
C Chen, D Zhang, PS Castro, N Li, L Sun, S Li
International Conference on Mobile and Ubiquitous Systems: Computing …, 2011
Dopamine: A research framework for deep reinforcement learning
PS Castro, S Moitra, C Gelada, S Kumar, MG Bellemare
arXiv preprint arXiv:1812.06110, 2018
Methods for computing state similarity in Markov decision processes
N Ferns, PS Castro, D Precup, P Panangaden
arXiv preprint arXiv:1206.6836, 2012
Using Linear Programming for Bayesian Exploration in Markov Decision Processes.
PS Castro, D Precup
IJCAI 24372442, 2007
TF-Agents: A library for reinforcement learning in tensorflow
S Guadarrama, A Korattikara, O Ramirez, P Castro, E Holly, S Fishman, ...
Real time anomalous trajectory detection and analysis
L Sun, D Zhang, C Chen, PS Castro, S Li, Z Wang
Mobile Networks and Applications 18 (3), 341-356, 2013
Equivalence relations in fully and partially observable Markov decision processes
PS Castro, P Panangaden, D Precup
Twenty-First International Joint Conference on Artificial Intelligence, 2009
Automatic construction of temporally extended actions for mdps using bisimulation metrics
PS Castro, D Precup
European Workshop on Reinforcement Learning, 140-152, 2011
Smarter sampling in model-based Bayesian reinforcement learning
PS Castro, D Precup
Joint European Conference on Machine Learning and Knowledge Discovery in …, 2010
Using bisimulation for policy transfer in MDPs
PS Castro, D Precup
Twenty-Fourth AAAI Conference on Artificial Intelligence, 2010
A comparative analysis of expected and distributional reinforcement learning
C Lyle, MG Bellemare, PS Castro
Proceedings of the AAAI Conference on Artificial Intelligence 33, 4504-4511, 2019
A geometric perspective on optimal representations for reinforcement learning
M Bellemare, W Dabney, R Dadashi, AA Taiga, PS Castro, N Le Roux, ...
Advances in Neural Information Processing Systems, 4358-4369, 2019
An atari model zoo for analyzing, visualizing, and comparing deep reinforcement learning agents
FP Such, V Madhavan, R Liu, R Wang, PS Castro, Y Li, J Zhi, L Schubert, ...
arXiv preprint arXiv:1812.07069, 2018
Distributional reinforcement learning with linear function approximation
MG Bellemare, NL Roux, PS Castro, S Moitra
arXiv preprint arXiv:1902.03149, 2019
Rigging the lottery: Making all tickets winners
U Evci, T Gale, J Menick, PS Castro, E Elsen
arXiv preprint arXiv:1911.11134, 2019
Scalable methods for computing state similarity in deterministic Markov Decision Processes
PS Castro
arXiv preprint arXiv:1911.09291, 2019
Notions of state equivalence under partial observability
PS Castro, P Panangaden, D Precup
Proceedings of the 21st International Joint Conference on Artificial …, 2009
The system can't perform the operation now. Try again later.
Articles 1–20